Li, Qianxiao

34 publications

NeurIPS 2025 A Unified Framework for Establishing the Universal Approximation of Transformer-Type Architectures Jingpu Cheng, Ting Lin, Zuowei Shen, Qianxiao Li

ICLR 2025 Autocorrelation Matters: Understanding the Role of Initialization Schemes for State Space Models Fusheng Liu, Qianxiao Li

ICLR 2025 BP-Modified Local Loss for Efficient Training of Deep Neural Networks Ren Lianhai, Qianxiao Li

ICLR 2025 Continuity-Preserving Convolutional Autoencoders for Learning Continuous Latent Dynamical Models from Images Aiqing Zhu, Yuting Pan, Qianxiao Li

ICML 2025 From Weight-Based to State-Based Fine-Tuning: Further Memory Reduction on LoRA with Parallel Control Chi Zhang, Ren Lianhai, Jingpu Cheng, Qianxiao Li

ICLRW 2025 Generative Subgrid-Scale Modeling Jiaxi Zhao, Sohei Arisaka, Qianxiao Li

ICML 2024 Accelerating Legacy Numerical Solvers by Non-Intrusive Gradient-Based Meta-Solving Sohei Arisaka, Qianxiao Li

ECCV 2024 An Optimal Control View of LoRA and Binary Controller Design for Vision Transformers Chi Zhang, Jingpu Cheng, Qianxiao Li

NeurIPS 2024 Approximation Rate of the Transformer Architecture for Sequence Modeling Haotian Jiang, Qianxiao Li

JMLR 2024 Deep Neural Network Approximation of Invariant Functions Through Dynamical Systems Qianxiao Li, Ting Lin, Zuowei Shen

ICML 2024 From Generalization Analysis to Optimization Designs for State Space Models Fusheng Liu, Qianxiao Li

ICLR 2024 Inverse Approximation Theory for Nonlinear Recurrent Neural Networks Shida Wang, Zhong Li, Qianxiao Li

NeurIPS 2024 Learning Macroscopic Dynamics from Partial Microscopic Observations Mengyi Chen, Qianxiao Li

TMLR 2024 PID Control-Based Self-Healing to Improve the Robustness of Large Language Models Zhuotong Chen, Zihu Wang, Yifan Yang, Qianxiao Li, Zheng Zhang

ICML 2024 Parameter-Efficient Fine-Tuning with Controls Chi Zhang, Cheng Jingpu, Yanyu Xu, Qianxiao Li

ICML 2024 StableSSM: Alleviating the Curse of Memory in State-Space Models Through Stable Reparameterization Shida Wang, Qianxiao Li

ICMLW 2023 Fairness in a Non-Stationary Environment from an Optimal Control Perspective Zhuotong Chen, Qianxiao Li, Zheng Zhang

ICML 2023 Principled Acceleration of Iterative Numerical Methods Using Machine Learning Sohei Arisaka, Qianxiao Li

NeurIPSW 2022 Accelerating the Discovery of Rare Materials with Bounded Optimization Techniques Alexander E. Siemenn, Zekun Ren, Qianxiao Li, Tonio Buonassisi

JMLR 2022 Approximation and Optimization Theory for Linear Continuous-Time Recurrent Neural Networks Zhong Li, Jiequn Han, Weinan E, Qianxiao Li

TMLR 2022 From Optimization Dynamics to Generalization Bounds via Łojasiewicz Gradient Inequality Fusheng Liu, Haizhao Yang, Soufiane Hayou, Qianxiao Li

ICLR 2022 On the Approximation Properties of Recurrent Encoder-Decoder Architectures Zhong Li, Haotian Jiang, Qianxiao Li

JMLR 2022 Self-Healing Robust Neural Networks via Closed-Loop Control Zhuotong Chen, Qianxiao Li, Zheng Zhang

ICLR 2022 Unraveling Model-Agnostic Meta-Learning via the Adaptation Learning Rate Yingtian Zou, Fusheng Liu, Qianxiao Li

CVPR 2021 Adversarial Invariant Learning Nanyang Ye, Jingxuan Tang, Huayu Deng, Xiao-Yun Zhou, Qianxiao Li, Zhenguo Li, Guang-Zhong Yang, Zhanxing Zhu

AAAI 2021 Amata: An Annealing Mechanism for Adversarial Training Acceleration Nanyang Ye, Qianxiao Li, Xiao-Yun Zhou, Zhanxing Zhu

ICML 2021 Approximation Theory of Convolutional Architectures for Time Series Modelling Haotian Jiang, Zhong Li, Qianxiao Li

ICLR 2021 On the Curse of Memory in Recurrent Neural Networks: Approximation and Optimization Analysis Zhong Li, Jiequn Han, Weinan E, Qianxiao Li

ICLR 2021 Towards Robust Neural Networks via Close-Loop Control Zhuotong Chen, Qianxiao Li, Zheng Zhang

ICML 2019 A Quantitative Analysis of the Effect of Batch Normalization on Gradient Descent Yongqiang Cai, Qianxiao Li, Zuowei Shen

IJCAI 2019 Decentralized Optimization with Edge Sampling Chi Zhang, Qianxiao Li, Peilin Zhao

JMLR 2019 Stochastic Modified Equations and Dynamics of Stochastic Gradient Algorithms I: Mathematical Foundations Qianxiao Li, Cheng Tai, Weinan E

ICML 2018 An Optimal Control Approach to Deep Learning and Applications to Discrete-Weight Neural Networks Qianxiao Li, Shuji Hao

ICML 2017 Stochastic Modified Equations and Adaptive Stochastic Gradient Algorithms Qianxiao Li, Cheng Tai, Weinan E